A methodology for multi-criteria information system design

Chandler, John S.; DeLutis, Thomas G.

doi:10.1145/1499402.1499565

Cited by 4 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This research was titled computer performance evaluation (NBS/ACM Workshop on Computer Performance Evaluation 1975). Later in the 1970s, Chandler and DeLutis (1977) studied multi-criteria information system design by stating: 'Ideally the system will perform optimally when it achieves its user oriented objectives within a minimum cost of the system'. These early studies introduced the idea of analysing both computer system (resource utilisation and queuing) and application or user system (throughput and response time) separately, but they did not introduce formulas indicating ways to connect these entities to assess overall system performance.…”

Section: Literature Reviewmentioning

confidence: 99%

Do flow principles of operations management apply to computing centres?

Abaunza¹,

Chavez‐Demoulin²,

Hameri³

et al. 2014

Production Planning & Control

View full text Add to dashboard Cite

By analysing large data-sets on jobs processed in major computing centres, we study how operations management principles apply to these modern day processing plants. We show that Little's Law on long-term performance averages holds to computing centres, i.e. work-in-progress equals throughput rate multiplied by process lead time. Contrary to traditional manufacturing principles, the law of variation does not hold to computing centres, as the more variation in job lead times the better the throughput and utilisation of the system. We also show that as the utilisation of the system increases lead times and work-in-progress increase, which complies with traditional manufacturing. In comparison with current computing centre operations these results imply that better allocation of jobs could increase throughput and utilisation, while less computing resources are needed, thus increasing the overall efficiency of the centre. From a theoretical point of view, in a system with close to zero set-up times, as in the case of computing centres, the law of variation does not hold. We observe that the more variation in job lead times and resource usage, the higher the throughput of the system.

show abstract

Section: Literature Reviewmentioning

confidence: 99%